This paper has proposed a data-driven approach to study the airflow swirl characteristics in industrial gas turbine combustion system. A grey-box model is developed to represent the combustion system characteristics, based on real gas turbine measurements. The model inputs are the burner tip temperatures, and the outputs are the downstream gas temperatures. Then, the model parameters are determined using a hybrid genetic algorithm–quasi-Newton optimization scheme. The efficacy of the proposed approach is demonstrated through a case study. It is shown that the proposed model can be a useful tool that adds to the existing array of gas turbine combustion monitoring applications.
History
School
Aeronautical, Automotive, Chemical and Materials Engineering
Mechanical, Electrical and Manufacturing Engineering
This paper was accepted for publication in the journal Measurement and the definitive published version is available at https://doi.org/10.1016/j.measurement.2019.107266.